Machine Learning Multiscale Interactions
2026-05-25 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a new machine learning model called MuSE to better understand physical systems that have important interactions happening at different sizes and times. Unlike other models that miss long-range effects, MuSE combines information from small and large scales using a special method to group atoms together smoothly. They tested MuSE with various existing models and showed it can accurately predict complex quantum interactions in molecules and materials. This makes MuSE useful for studying things like biomolecule folding or interactions in nanostructures.
machine learning force fieldsmultiscale modelingcoarse-grainingmessage-passing layersquantum mechanicsbiomolecule foldingnanostructuresHessian benchmarksSO3kratesMACE
Authors
Àlex Solé, Sergio Suárez-Dou, Albert Mosella-Montoro, Silvia Gómez-Coca, Eliseo Ruiz, Alexandre Tkatchenko, Javier Ruiz-Hidalgo
Abstract
Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models.